Jianguo Zhang, Kun-Yu Lin, Wei-Shi Zheng, Jian-Fang Hu, Chaolei Tan, Tianming Liang
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.
Referring video object segmentation (RVOS) aims to segment target objects throughout a video based on a text description. This is challenging as it involves deep visionlanguage understanding, pixel-level dense prediction and spatiotemporal reasoning. Despite notable progress in recent years, existing methods still exhibit a noticeable gap when considering all these aspects. In this work, we propose ReferDINO, a strong RVOS model that inherits region-level vision-language alignment from foundational visual grounding models, and is further endowed with pixellevel dense perception and cross-modal spatiotemporal reasoning. In detail, ReferDINO integrates two key components: 1) a grounding-guided deformable mask decoder that utilizes location prediction to progressively guide mask prediction through differentiable deformation mechanisms; 2) an object-consistent temporal enhancer that injects pretrained time-varying text features into inter-frame interaction to capture object-aware dynamic changes. Moreover, a confidence-aware query pruning strategy is designed to accelerate object decoding without compromising model performance. Extensive experimental results on five benchmarks demonstrate that our ReferDINO significantly outperforms previous methods (e.g., +3.9% J &F on Ref-YouTube-VOS) with real-time inference speed (51 FPS).
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2501.14607")
get_code_for_paper("2501.14607")
have("2501.14607")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2501.14607.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2501.14607)
Connect an agent — have() is free.